Repositories taking off
?
- Stars gained
- New stars in the window. "all" means the repo is younger than the window, so the number is every star it has.
- Today
- Stars since midnight US Pacific time, so a partial day.
- Above pace
- How many more stars the repo got than its pace in the window before would predict. +500 means 500 more than usual.
- Momentum
- A daily score modeled on trendshift.io: 8 points per star and 2 per fork since midnight UTC, reduced for repos that are this busy every day.
- Speed-up
- Stars per day in the window divided by stars per day in the window before. "New" means the repo is younger than the window. "Under 14 days" (twice the window; "Under 2 years" for 1 year) means it is older than the window but too young for a full window before it to compare with.
- Bars
- Stars per day (per week for 90 days and 1 year). Bright bars are the selected window. Heights use a square-root scale, so quieter days stay visible next to a spike.
Updated 54 min ago
Columns
| # | Repository | Stars | Today | 7d | 30d | Above pace ↓ | Momentum | Speed-up | Daily stars |
|---|---|---|---|---|---|---|---|---|---|
| 501 |
Static recompiler that turns Nintendo Switch executables into native PC programs, written in Rust. |
49 | +7 | +49all | +49all | +7 | 58 | Up from 0 | |
| 502 |
Steal-a-Brainrot-Scripts-(SAB)-pc-desktop |
133 | 0 | +102all | +102all | +7 | 0 | No data | |
| 503 |
Open-source, cross-platform AI quota monitor (Codex, Claude, Cursor and 47 more). Windows, macOS, Linux, Android and iOS. Built with Flutter. |
74 | +14 | +74all | +74all | +7 | 118 | 2.1x faster | |
| 504 |
Apache Kafka - A distributed event streaming platform |
34,128 | +7 | +54 | +354 | +6 | 96 | 5.2x faster | |
| 505 |
Odoo. Open Source Apps To Grow Your Business. |
55,329 | +9 | +182 | +734 | +6 | 61 | 3.1x faster | |
| 506 |
Animation engine for explanatory math videos |
95,673 | +12 | +298 | +1,509 | +6 | 85 | 1.9x faster | |
| 507 |
World's fastest and most advanced password recovery utility |
27,117 | +16 | +93 | +280 | +6 | 352 | 1.5x faster | |
| 508 |
A collection of various awesome lists for hackers, pentesters and security researchers |
123,674 | +25 | +592 | +2,746 | +6 | 214 | 1.3x faster | |
| 509 |
The fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible. |
41,068 | +7 | +102 | +421 | +6 | 50 | 10.5x faster | |
| 510 |
:file_folder: Universal File Management Platform (for humans and agents) |
14,829 | +6 | +22 | +132 | +6 | 48 | Up from 0 | |
| 511 |
Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more |
38,729 | +10 | +208 | +702 | +6 | 90 | 2.2x faster | |
| 512 |
A general-purpose window upscaler for Windows 10/11. |
16,106 | +11 | +193 | +1,138 | +6 | 98 | 2.1x faster | |
| 513 |
The self-improving agent platform |
42,899 | +8 | +86 | +630 | +6 | 96 | 3.6x faster | |
| 514 |
小说下载｜网文下载 | 网络小说 |
8,776 | +8 | +93 | +567 | +6 | 88 | 4.0x faster | |
| 515 |
Contains Solutions and Notes for the Machine Learning Specialization By Stanford University and Deeplearning.ai - Coursera (2022) by Prof. Andrew NG |
8,099 | +8 | +56 | +162 | +6 | 82 | 4.5x faster | |
| 516 |
🤖 可 DIY 的 多模态 AI 聊天机器人 | 🚀 快速接入 微信、 QQ、Telegram、等聊天平台 | 🦈支持DeepSeek、Grok、Claude、Ollama、Gemini、OpenAI | 工作流系统、网页搜索、AI画图、人设调教、虚拟女仆、语音对话 | |
19,197 | +8 | +91 | +210 | +6 | 88 | 3.6x faster | |
| 517 |
免费大模型API，支持免费调用GPT、DeepSeek等主流模型，免费额度10000点，每日刷新！另付费价格最低官方1-2折！ |
44,888 | +20 | +385 | +1,849 | +6 | 227 | 1.5x faster | |
| 518 |
X-AnyLabeling: A lightweight, efficient, and unified cross-platform desktop application for annotating text, image, video, point cloud and multimodal data, combining versatile built-in tools with state-of-the-art AI models and flexible multi-format export. |
10,809 | +8 | +68 | +284 | +6 | 114 | 3.3x faster | |
| 519 |
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol |
38,247 | +10 | +135 | +782 | +6 | 158 | 2.5x faster | |
| 520 |
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. |
184,830 | +32 | +978 | +3,660 | +6 | 345 | 1.2x faster | |
| 521 |
Industry leading face manipulation platform |
30,409 | +8 | +100 | +447 | +6 | 79 | 3.3x faster | |
| 522 |
User-friendly AI Interface (Supports Ollama, OpenAI API, ...) |
156,797 | +27 | +634 | +4,147 | +6 | 215 | 1.3x faster | |
| 523 |
Typescript/React Library for AI Chat 💬🚀 |
12,752 | +8 | +122 | +462 | +6 | 77 | 3.3x faster | |
| 524 |
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs |
92,893 | +18 | +413 | +1,733 | +6 | 232 | 1.5x faster | |
| 525 |
Boss直聘助手-优化UI去除广告,批量投递简历,高级筛选,GPT自动打招呼,多账号管理... |
2,410 | +8 | +49 | +163 | +6 | 120 | 3.6x faster | |
| 526 |
The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more. |
25,822 | +8 | +86 | +482 | +6 | 128 | 3.6x faster | |
| 527 |
🧠 Train a 64M-parameter LLM from scratch in just 2h! |
64,439 | +16 | +449 | +1,898 | +6 | 151 | 1.6x faster | |
| 528 |
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels |
8,782 | +8 | +127 | +1,316 | +6 | 110 | 3.3x faster | |
| 529 |
🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev |
89,800 | +50 | +1,109 | +6,134 | +6 | 436 | 1.1x faster | |
| 530 |
洛雪音乐源 |
10,265 | +15 | +263 | +1,075 | +6 | 166 | 1.7x faster | |
| 531 |
Model Context Protocol Servers |
91,578 | +11 | +206 | +1,166 | +6 | 118 | 2.4x faster | |
| 532 |
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more. |
12,153 | +8 | +88 | +267 | +6 | 84 | 3.3x faster | |
| 533 |
MCP server for interfacing with Godot game engine. Provides tools for launching the editor, running projects, and capturing debug output. |
6,364 | +11 | +170 | +555 | +6 | 101 | 2.4x faster | |
| 534 |
KiCAD MCP is a Model Context Protocol (MCP) implementation that enables Large Language Models (LLMs) like Claude to directly interact with KiCAD for printed circuit board design. |
2,957 | +9 | +89 | +493 | +6 | 104 | 3.4x faster | |
| 535 |
Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly. |
70,241 | +19 | +380 | +2,116 | +6 | 219 | 1.4x faster | |
| 536 |
Open-Source AI Presentation Generator and API (Gamma, Canva, Beautiful AI, Decktopus, Presentations AI Alternative) |
11,368 | +14 | +142 | +613 | +6 | 218 | 1.8x faster | |
| 537 |
bluetooth mesh chat, IRC vibes |
36,849 | +13 | +212 | +647 | +6 | 143 | 1.9x faster | |
| 538 |
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support. |
12,105 | +9 | +159 | +545 | +6 | 91 | 2.7x faster | |
| 539 |
The batteries-included agent harness. |
30,603 | +12 | +178 | +870 | +6 | 186 | 2.1x faster | |
| 540 |
Agentic Development Environment based on OpenCode AI agent |
12,190 | +13 | +307 | +1,592 | +6 | 147 | 1.8x faster | |
| 541 |
Residential, datacenter, ISP & mobile proxies with 90M+ IPs in 200+ countries — plus Scraper & SERP APIs. Code examples in Python, Node.js, PHP, Go, Java, C#, Ruby and curl. |
841 | +19 | +154 | +403 | +6 | 296 | 1.5x faster | |
| 542 |
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞 |
393,116 | +30 | +865 | +4,383 | +6 | 307 | 1.2x faster | |
| 543 |
Open source AI clip generator: turns long videos into viral 9:16 shorts with AI moment detection, face tracking, subtitles and dubbing. Self-host free with Docker (MIT), or use the cloud with GPU speed from $12/mo. MCP server and API for AI agents. |
7,105 | +12 | +237 | +1,437 | +6 | 108 | 2.0x faster | |
| 544 |
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents. |
27,660 | +10 | +134 | +615 | +6 | 125 | 2.4x faster | |
| 545 |
Teams-first Multi-agent orchestration for Claude Code |
40,281 | +13 | +209 | +1,081 | +6 | 116 | 1.9x faster | |
| 546 |
No description |
26,970 | +12 | +193 | +852 | +6 | 151 | 2.2x faster | |
| 547 |
The open-source AI voice studio. Clone, dictate, create. |
58,576 | +22 | +559 | +2,978 | +6 | 208 | 1.4x faster | |
| 548 |
Elevate your AI research writing, no more tedious polishing ✨ |
35,270 | +12 | +253 | +942 | +6 | 128 | 2.1x faster | |
| 549 |
Open-source (Apache-2.0) orchestrator for Claude Code, Codex & 30+ coding agents. Plan, run and supervise agent teams from task to merged PR. Desktop (macOS, Windows, Linux) + iPhone & Android apps. |
13,674 | +19 | +289 | +1,337 | +6 | 281 | 1.4x faster | |
| 550 |
Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant from anywhere — no public IP required for most platforms. |
16,099 | +7 | +104 | +479 | +6 | 104 | 5.2x faster |
Today counts stars since midnight US Pacific time, so it is a partial day. 597 more tracked repositories are still loading their star history and will join the ranking once it is complete.